Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks

Ladder networks are a notable new concept in the field of semi-supervised learning by showing state-of-the-art results in image recognition tasks while being compatible with many existing neural architectures. We present the recurrent ladder network, a novel modification of the ladder network, for semi-supervised learning of recurrent neural networks which we evaluate with a phoneme recognition task on the TIMIT corpus. Our results show that the model is able to consistently outperform the baseline and achieve fully-supervised baseline performance with only 75% of all labels which demonstrates that the model is capable of using unsupervised data as an effective regulariser.

@InProceedings{TATW17, 
 	 author =  {Tietz, Marian and Alpay, Tayfun and Twiefel, Johannes and Wermter, Stefan},  
 	 title = {Semi-Supervised Phoneme Recognition with Recurrent Ladder Networks}, 
 	 booktitle = {Proceedings of the 26th International Conference on Artificial Neural Networks (ICANN 2017)},
 	 editors = {Villa, Alessandro E.P. and Masulli, Paolo and Pons Rivero, Antonio Javier},
 	 number = {},
 	 volume = {},
 	 pages = {},
 	 year = {2017},
 	 month = {Sep},
 	 publisher = {Springer International Publishing},
 	 doi = {10.1007/978-3-319-68600-4_1}, 
 }